BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20251102T010000
RDATE:20260308T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20261101T010000
RDATE:20270314T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20271107T010000
RDATE:20280312T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20281105T010000
RDATE:20290311T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250922T100000
RDATE:20251102T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20261101T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20270314T030000
RDATE:20271107T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20280312T030000
RDATE:20281105T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:7f1e09a1d76cca433a49e9b7d1893de8
CATEGORIES:Lean Seminar
CREATED:20260916T160335
SUMMARY:Toward Reliable AI-Assisted Mathematics
LOCATION:Hill 705
DESCRIPTION:Speaker: Qihao Ye (Columbia) Title: Toward Reliable AI-Assisted Mathematics
 \nAbstract: This talk explores how AI can support literature review, proof 
 development, and verification, emphasizing practical, affordable workflows 
 for individual researchers. I will examine seven recurring failure modes an
 d introduce QED, an open-source multi-agent system designed to address them
 . As a concrete case study, I will discuss the AI-assisted construction of 
 Carleman weights for wave equations on the half-line, illustrating how indi
 vidual researchers can combine AI-assisted search with their own mathematic
 al insight and rigorous verification. The QED implementation is available a
 t https://github.com/proofQED/QED (https://github.com/proofQED/QED), and th
 e case-study paper is available at https://arxiv.org/abs/2609.06283. (https
 ://arxiv.org/abs/2609.06283.)
X-ALT-DESC;FMTTYPE=text/html:<div data-olk-copy-source="MessageBody" style="border: 0px; font-style: nor
 mal; font-weight: 400; font-size: 12pt; line-height: inherit; font-family: 
 Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-se
 rif; margin: 0px; padding: 0px; vertical-align: baseline; letter-spacing: n
 ormal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-
 spacing: 0px; white-space: normal; text-align: left;">Speaker: Qihao Ye (Co
 lumbia)</div><div style="border: 0px; font-style: normal; font-weight: 400;
  font-size: 12pt; line-height: inherit; font-family: Aptos, Aptos_EmbeddedF
 ont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; margin: 0px; padd
 ing: 0px; vertical-align: baseline; letter-spacing: normal; orphans: 2; tex
 t-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; white-sp
 ace: normal; text-align: left;">&nbsp;</div><div style="border: 0px; font-s
 tyle: normal; font-weight: 400; font-size: 12pt; line-height: inherit; font
 -family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica
 , sans-serif; margin: 0px; padding: 0px; vertical-align: baseline; letter-s
 pacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows:
  2; word-spacing: 0px; white-space: normal; text-align: left;">Title: Towar
 d Reliable AI-Assisted Mathematics</div><div style="border: 0px; font-style
 : normal; font-weight: 400; font-size: 12pt; line-height: inherit; font-fam
 ily: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sa
 ns-serif; margin: 0px; padding: 0px; vertical-align: baseline; letter-spaci
 ng: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; 
 word-spacing: 0px; white-space: normal; text-align: left;"><br>Abstract: Th
 is talk explores how AI can support literature review, proof development, a
 nd verification, emphasizing practical, affordable workflows for individual
  researchers. I will examine seven recurring failure modes and introduce QE
 D, an open-source multi-agent system designed to address them. As a concret
 e case study, I will discuss the AI-assisted construction of Carleman weigh
 ts for wave equations on the half-line, illustrating how individual researc
 hers can combine AI-assisted search with their own mathematical insight and
  rigorous verification. The QED implementation is available at&nbsp;<a href
 ="https://github.com/proofQED/QED">https://github.com/proofQED/QED</a>, and
  the case-study paper is available at&nbsp;<a href="https://arxiv.org/abs/2
 609.06283.">https://arxiv.org/abs/2609.06283.</a></div>
X-EXTRAINFO:Zoom Link: https://rutgers.zoom.us/j/94999749212?pwd=mBADyoubpVrIexy6X34S6n
 j47ft316.1\n\nPasscode: 516100
DTSTAMP:20261001T055452
DTSTART;TZID=America/New_York:20260923T100000
DTEND;TZID=America/New_York:20260923T110000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR